基于数据压缩的无人机边缘计算卸载优化

Offloading Optimization Based on Data Compression in UAV-Assisted Edge Computing

数据压缩技术通过压缩计算任务可以降低移动边缘计算(Mobile edge computing,MEC)网络中终端用户的卸载能耗。针对终端用户与基站之间的通信链路被障碍物阻挡对通信质量有影响问题,为满足应急通信和节能卸载需求,提出了一种无人机搭载中继设备和边缘服务器辅助MEC中基于数据压缩的任务卸载方案。考虑任务压缩比例、系统资源和无人机机载能量等约束条件,建立用户总能耗最小化问题。将该非凸优化问题建模成一个马尔可夫决策过程,使用深度强化学习中柔性演员?评论家算法求解。仿真结果表明,所提方案具有良好的收敛性,与基准算法相比,能耗降低了24.7%~42.2%。

Data compression technology can reduce the offloading energy consumption of users in mobile edge computing(MEC)by compressing computing tasks.Aiming at the problem that the communication link between the mobile users and the base station is blocked,which has an impact on communication quality,this paper proposes a task offloading scheme based on data compression to meet the requirements of emergency communication and energy-saving offloading in MEC assisted by the unmanned aerial vehicle(UAV)equipped with relay devices and edge servers.Considering constraints such as task compression ratios,system resource and the onboard energy of UAV,we formulate a problem to minimize the sum energy consumption of users.The non-convex optimization problem is modeled as a Markov decision process and the soft actor-critic algorithm based deep reinforcement learning is used to tackle the problem.The simulation results reveal that the proposed scheme achieves better convergence performance and the total energy consumption of users can be reduced by 24.7%—42.2%,compared with the benchmark algorithms.